Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/21852#discussion_r206739216 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala --- @@ -416,6 +416,24 @@ object SimplifyConditionals extends Rule[LogicalPlan] with PredicateHelper { // these branches can be pruned away val (h, t) = branches.span(_._1 != TrueLiteral) CaseWhen( h :+ t.head, None) + + case e @ CaseWhen(branches, Some(elseValue)) + if branches.forall(_._2.semanticEquals(elseValue)) => + // For non-deterministic conditions with side effect, we can not remove it, or change + // the ordering. As a result, we try to remove the deterministic conditions from the tail. + var hitNonDeterministicCond = false + var i = branches.length + while (i > 0 && !hitNonDeterministicCond) { + hitNonDeterministicCond = !branches(i - 1)._1.deterministic + if (!hitNonDeterministicCond) { --- End diff -- nit: we can avoid this per-iteration `if` check by updating the final step ``` if (i == 0 && !hitNonDeterministicCond) { elseValue } else { e.copy(branches = branches.take(i + 1).map(branch => (branch._1, elseValue))) } ``` feel free to change it in your next PR.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org